ExPeerience: Towards AI-Assisted Learnersourcing to Bridge Conceptual Understanding and Problem Solving in Database Programming EducationLearnersourcing, an educational approach that positions students as active contributors rather than passive consumers, offers a scalable approach to co-creating instructional resources while engaging students in authentic problem-solving. However, it faces a fundamental tension: effective ``learning'' requires scaffolding that minimizes extraneous cognitive load and focuses attention on reasoning, while effective ``sourcing'' requires structure, completeness, and standardization to ensure student-generated content can be reused. These competing goals create a tradeoff: students either learn but produce content that is difficult to reuse, or generate usable resources but receive limited learning benefit. We propose a new AI-assisted learnersourcing paradigm to address this tension. By assigning collaborative roles to both learners and AI, the approach enables students to focus on cognitively meaningful sub-tasks that foster ``learning'', while large language models (LLMs) handle mechanical and procedural sub-tasks for ``sourcing''. Guided by user-centered design principles, we implement this workflow in ExPeerience, a system that scaffolds students in co-creating contextualized worked-out examples for database programming. Within ExPeerience, the AI serves as a collaborator for ideation, a co-creator of artifacts, and an evaluator of students' inputs. Our evaluation with 24 participants showed that structuring AI into distinct collaborative roles improves learning engagement while producing high-quality student-generated content. Compared to a baseline using the Gemini chatbot, ExPeerience users created SQL problems in more diverse and personally meaningful contexts. They actively evaluated, edited, and refined AI-generated components, and most authored their own SQL solutions, whereas baseline participants largely accepted AI outputs without modification and did not attempt to solve the problem. Overall, ExPeerience produced more contextualized, varied, and thoughtfully constructed worked-out examples. These findings demonstrate the potential of AI-assisted learnersourcing as a paradigm to balance learning and sourcing goals. We also draw design implications for future AI-assisted learnersourcing systems that aim to produce reusable, high-quality learner-generated content while promoting educational value.2026YZYuzhe Zhou et al.Purdue UniversityIntelligent Tutoring Systems & Learning AnalyticsHuman-LLM CollaborationProgramming Education & Computational ThinkingIUI
Canvas3D: Empowering Precise Spatial Control for Image Generation with Constraints from a 3D Virtual CanvasGenerative AI (GenAI) has significantly advanced the ease and flexibility of image creation. However, it remains a challenge to precisely control spatial compositions, including object arrangement and scene conditions. To bridge this gap, we propose Canvas3D, an interactive system leveraging a 3D engine to enable precise spatial manipulation for image generation. Upon user prompt, Canvas3D automatically converts textual descriptions into interactive objects within a 3D engine-driven virtual canvas, empowering direct and precise spatial configuration. These user-defined arrangements generate explicit spatial constraints that guide generative models in accurately reflecting user intentions in the resulting images. We conducted a closed-ended comparative study between Canvas3D and a baseline system, and an open-ended, free-form study to assess overall system usability. The results indicate that Canvas3D outperforms the baseline on spatial control, interactivity, and overall user experience.2026YCYuzhao Chen et al.Purdue UniversityGenerative AI (Text, Image, Music, Video)3D Modeling & AnimationCreative Collaboration & Feedback SystemsIUI
Privacy is Not One-Click: Designing Robots That Adapt to Older Adults’ Changing Boundaries Social robots in the home bring new privacy risks and concerns for older adults. Yet, current technology privacy mechanisms typically use a one-time and universal consent mechanism (e.g., user agreement checkbox, browser cookie setting, etc.), lacking consideration of how privacy is holistically experienced. Designing for privacy requires a multidimensional approach to support how older adults experience privacy. To investigate older adult-centered privacy mechanisms for social robots, we conducted two participatory design (PD) workshops at local assisted living facilities. Our findings from these workshops suggest that older adults do not treat privacy as static, but as a temporal and situational practice that requires continuous negotiations and revisions. We subsequently conducted a post-PD speculative design (SD) process that extracted three design features for privacy—aware social robots-privacy profiles, real-time privacy feedback, and data ownership tools—that can support older adults’ multidimensional privacy experiences.2026NJNishchal Jagadeesha et al.Purdue UniversitySocial Robot InteractionPrivacy by Design & User ControlAging-in-Place Assistance SystemsCHI
Understanding Gendered Experiences of Harassment Among Pakistani Young Adults Using Human-Centered Threat ModelingHarassment impacts the safety and well-being of young adults in Pakistan. Prior research has largely focused on women, often imposing external definitions of harm and overlooking how individuals themselves understand and respond to harassment. This study examines how Pakistani young adults define, experience, and cope with harassment. Drawing on 33 semi-structured interviews guided by a human-centered threat modeling framework, we surface context-specific threat models. Participants’ definitions of harassment were shaped by gender norms, religious values, and moral judgments. Women described harassment as a routine part of life, tied to public visibility, modesty norms. Men also reported harassment, though framed by different dynamics such as pressure to maintain control, avoid vulnerability, and conform to masculinity. Across participants, formal reporting pathways were viewed as untrustworthy or unsafe. Our findings highlight the need for interventions that reflect local definitions of harm, address relational adversaries, and support safety within sociocultural contexts.2026WUWarda Usman et al.Brigham Young UniversityOnline Harassment & Counter-ToolsGender & Race Issues in HCIEmpowerment of Marginalized GroupsCHI
Towards Interface Design for Parrot-Human Communication: Investigating Parrot Selections of Speech Board RepresentationsParrots have shown the ability to interact with tablet-based speech boards to engage in parrot-human communication. However, the influence of speech boards’ interface design on avian usability and, thus, on speech boards’ potential to optimally support parrot-human communication, is yet to be explored. As a first step in this direction, we report on a longitudinal four-year in-the-wild study of a Goffin’s Cockatoo's interactions with three successive speech board interfaces. The study explored, for the first time, possible relations between interface design variables typically considered for human speech board users - type, granularity, repertoire and arrangement of speech board representations - and the bird's selections under different conditions and across different design iterations. Based on our findings, we contribute key considerations and hypotheses to inform further research into the relevance of interface design choices for the avian usability of speech boards and, thus, their potential to optimally support functional parrot-human communication.2026CMClara Mancini et al.The Open UniversityParticipatory DesignPrototyping & User TestingTangible User Interface DesignCHI
HieraVisVR: Hierarchical Visual Analytics for Motion-Centric VR PlaytestingPlaytesting is widely used in the game industry to identify design flaws and evaluate player experience, yet little research explores how to effectively visualize and analyze playtesting data. This challenge is particularly pronounced in motion-based VR games, which involve physical movements and interactions tracked through multimodal inputs, resulting in complex multidimensional data. To better understand the challenges designers face, we conducted a formative study with 30 practitioners in the VR domain to characterize playtesting workflows and associated tasks. Based on these findings, we present HieraVisVR, a hierarchical visual analytics framework that incorporates body-motion-related data to help designers identify player behaviors and critical game moments, thereby simplifying their workflow. We demonstrate the applicability of HieraVisVR in three different applications and evaluate our system with playtesting experts through an analysis of motion-based game data. The study results suggest that our system enhances playtesters' understanding of the gameplay and improves their data analysis workflow. playtest results of VR games in a top-down manner.2026YZYongqi Zhang et al.George Mason UniversitySocial & Collaborative VRImmersion & Presence ResearchGame UX & Player BehaviorCHI
Talking Inspiration: A Discourse Analysis of Data Visualization PodcastsData visualization practitioners routinely invoke inspiration, yet we know little about how it is constructed in public conversations. We conduct a discourse analysis of 31 episodes from five popular data visualization podcasts. Podcasts are public-facing and inherently performative: guests manage impressions, articulate values, and model “good practice” for broad audiences. We use this performative setting to examine how legitimacy, identity, and practice are negotiated in community talk. We show that “inspiration talk” is operative rather than ornamental: speakers legitimize what counts, who counts, and how work proceeds. Our analysis surfaces four adjustable evaluation criteria by which inspiration is judged—novelty, authority, authenticity, and affect—and three operative metaphors that license different practices—spark, muscle, and resource bank. We argue that treating inspiration as a boundary object helps explain why these frames coexist across contexts. Findings provide a vocabulary for examining how inspiration is mobilized in visualization practice, with implications for evaluation, pedagogy, and the design of galleries and repositories that surface inspirational examples.2026ABAli Baigelenov et al.Purdue UniversityInteractive Data VisualizationData StorytellingVisualization Perception & CognitionCHI
Not Seeing the Whole Picture: Challenges and Opportunities in Using AI for Co-Making Physical, DIY-AT for People with Visual ImpairmentsExisting assistive technologies (AT) often adopt a one-size-fits-all approach, overlooking the diverse needs of people with visual impairments (PVI). Do-it-yourself AT (DIY-AT) toolkits offer one path toward customization, but most remain limited—targeting co-design with engineers or requiring programming expertise. Non-professionals with disabilities, including PVI, also face barriers such as inaccessible tools, lack of confidence, and insufficient technical knowledge. These gaps highlight the need for prototyping technologies that enable PVI to directly make their own AT. Building on emerging evidence that large language models (LLMs) can serve not only as visual aids but also as co-design partners, we present an exploratory study of how LLM-based AI can support PVI in the tangible DIY-AT co-making process. Our findings surface key challenges and design opportunities: the need for greater spatial and visual support, strategies for mitigating novel AI errors, and implications for designing more accessible AI-assisted prototypes.2026BKBen Kosa et al.University of Wisconsin--MadisonElectrical Muscle Stimulation (EMS)Generative AI (Text, Image, Music, Video)Explainable AI (XAI)CHI
JustShape: Exploring Co-Speech Gestures for Multimodal LLM-Powered 3D Parametric ModelingParametric modeling is a prevailing 3D modeling approach in design, architecture, and engineering. The emergence of multimodal large language models (LLMs) brings a new opportunity to lower the entry barriers to this powerful tool. However, describing 3D geometries through natural language can be fuzzy and challenging. We introduce co-speech gesture, a natural and expressive interaction modality to complement text prompts for LLM-empowered generative parametric modeling. We first conducted an elicitation study to explore and categorize co-speech gesture expressions. Based on the findings, we designed a multimodal fusion pipeline that parametrizes gestures and synthesizes them with speech. This approach reduces language ambiguity by translating implicit user intentions into explicit parametric attributes, thus lifting the model generation performance. We conducted a two-session user study testing and comparing it with traditional language and sketch inputs. This work streamlines the parametric modeling workflow and explores novel multimodal interaction paradigms for LLM-empowered design and creation.2026RDRunlin Duan et al.Purdue UniversityHand Gesture RecognitionGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCHI
VizCrit: Exploring Strategies for Displaying Computational Feedback in a Visual Design ToolVisual design instructors often provide multi-modal feedback, mixing annotations with text. Prior theory emphasizes the importance of actionable feedback, where “actionability” lies on a spectrum—from surfacing relevant design concepts to suggesting concrete fixes. How might creativity tools implement annotations that support such feedback, and how does the actionability of feedback impact novices’ process-related behaviors, perceptions of creativity, learning of design principles, and overall outcomes? We introduce VizCrit, a system for providing computational feedback that supports the actionability spectrum, realized through algorithmic issue detection and visual annotation generation. In a between-subjects study (N=36), novices revised a design under one of three conditions: textbook-based, awareness-centered, or solution-centered feedback. We found that solution-centered feedback led to fewer design issues and higher self-perceived creativity compared with textbook-based feedback, although expert ratings on creativity showed no significant differences. We discuss the implications for AI in Creativity Support Tools, including the potential of calibrating feedback actionability to help novices balance productivity with learning, growth, and developing design awareness.2026MLMingyi Li et al.Northeastern UniversityGenerative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsCHI
Radical Gender Neutrality: Agender Euphoria in Gaming and Play ExperiencesAgender euphoria is a new term representing the powerful feelings of happiness, joy, and contentment derived from experiences in gender-free embodiments, spaces, and activities. People with and without agender and adjacent identities (e.g., genderless, gender-free, non-binary, gender-apathetic) may have such experiences under the right circumstances. Video games can offer gender minorities a safe haven for gender euphoric experiences. However, the possibility of agender euphoric experiences was unexplored. We considered this overlooked frame of self-actualization with 142 people who identified as having or desiring agender euphoric experiences. Using the critical incident technique (CIT), we uncovered how games and play experiences create (and inhibit) agender euphoria. We surface this experiential phenomenon and provide empirically-grounded criteria for the design of games to elicit agender euphoric experiences for everyone, but especially agender and agender adjacent players. This work adds to the growing critical literatures on marginalized experiences in games research and human-computer interaction.2026KSKatie Seaborn et al.Institute of Science TokyoGame UX & Player BehaviorGender & Race Issues in HCIEmpowerment of Marginalized GroupsCHI
Understanding the Effects of AI-Assisted Critical Thinking on Human-AI Decision MakingDespite the growing prevalence of human-AI decision making, the human-AI team’s decision performance often remains suboptimal, partially due to insufficient examination of humans’ own reasoning. In this paper, we explore designing AI systems that directly analyze humans' decision rationales and encourage critical reflection of their own decisions. We introduce the AI-Assisted Critical Thinking (AACT) framework, which leverages a domain-specific AI model’s counterfactual analysis of human decision to help decision-makers identify potential flaws in their decision argument and support the correction of them. Through a case study on house price prediction, we find that AACT outperforms traditional AI-based decision-support in reducing over-reliance on AI, though also triggering higher cognitive load. Subgroup analysis reveals AACT can be particularly beneficial for some decision-makers such as those very familiar with AI technologies. We conclude by discussing the practical implications of our findings, use cases and design choices of AACT, and considerations for using AI to facilitate critical thinking.2026HTHarry Yizhou Tian et al.Purdue UniversityAI-Assisted Decision-Making & AutomationExplainable AI (XAI)CHI
AgentHands: Generating Interactive Hand Gestures for Spatially Grounded Agent Conversations in XRCommunicating spatial tasks via text or speech creates ``a mental mapping gap'' that limits an agent’s expressiveness. Inspired by co-speech gestures in face-to-face conversation, we propose \textsc{AgentHands}, an LLM-powered XR system that equips agents with hands to render responses clearer and more engaging. Guided by a design taxonomy distilled from a formative study (N=10), we implement a novel pipeline to generate and render a hand agent that augments conversational responses with synchronized, space-aware, and interactive hand gestures: using a meta-instruction, \textsc{AgentHands} generates verbal responses embedded with \textit{GestureEvents} aligned to specific words; each event specifies gesture type and parameters. At runtime, a parser converts events into time-stamped poses and motions, driving an animation system that renders expressive hands synchronized with speech. In a within-subjects study (N=12), \textsc{AgentHands} increased engagement and made spatially grounded conversations easier to follow compared to a speech-only baseline.2026ZLZiyi Liu et al.Purdue UniversityIdentity & Avatars in XRAffective Human-Computer DialogueImmersion & Presence ResearchCHI
ARify: Leveraging Narrated Instructional Videos to Create Augmented Reality Tutorials for Procedural TasksAugmented Reality (AR) tutorials enhance procedural task learning by providing situated, step-by-step guidance. Yet, creating such tutorials requires AR authoring expertise, posing a significant entry barrier. To lower this barrier, we introduce ARify, an authoring system that semi-automatically transforms narrated instructional videos into AR tutorials. To guide system design, we conducted a content analysis of video tutorials and derived a design space of instructional intents, tactics, and AR representations. Building on this, ARify generates AR tutorials by integrating a vision–language model to plan tutorial structures and an AR builder to configure AR representations, and offers interfaces that allow users to refine and customize the results. A numerical study on three machine tasks and a user study with 18 participants showed that ARify achieves promising performance across task types, and allows novices to author effective AR tutorials, validating its effectiveness and usability.2026XHXiyun Hu et al.Purdue UniversityAR Navigation & Context AwarenessPrototyping & User TestingMixed Reality WorkspacesCHI
Large Language Model (LLM)-driven Adversarial Social Influences in Online Information Spread: Risks and InterventionsPeople's online information processing is strongly shaped by social influence, and large language models (LLMs) now enable social bots to manipulate such influence at scale. This paper examines the effects of LLM-driven adversarial social influence—a strategy in which automated agents employ LLMs to distort truth by making misinformation appear credible or by undermining factual news—on how people evaluate and share information. Across two pre-registered, randomized experiments, we first show that exposure to LLM-driven adversarial social influence significantly reduces people's ability to judge the veracity of news and lowers their discernment between sharing true versus false content. We then test two credibility prompts: AI-generated content detectors and warnings, as potential interventions. Results show that both prompts mitigate some harms such as by improving misinformation detection, though their effectiveness were dependent on the context. We conclude by discussing the risks of LLM-driven adversarial social bots and the implications for designing interventions to combat misinformation.2026ZLZhuoran Lu et al.Purdue UniversityHuman-LLM CollaborationMisinformation & Fact-CheckingExplainable AI (XAI)CHI
AgentCoach: LLM-Based Adaptive Coaching Feedback for Motor Skill LearningWe present AgentCoach, an LLM-powered system that provides adaptive feedback for motor skill learning from tutorial videos. The system works by extracting key coaching points (CPs) and compiling CP-specific evaluators that map each cue to measurable kinematic parameters. This process allows AgentCoach to connect high-level semantic meaning with low-level postural estimation for accurate, context-aware evaluation. During practice, learners receive concise visual diagnostics of their mistakes paired with prescriptive verbal feedback that adapts based on their performance history. We technically validate the CP extraction and evaluator compilation across a wide range of common sports and exercise videos. A user study confirms the system's usability and shows the system's potential effectiveness of its adaptive feedback across multiple skills.2026DMDizhi Ma et al.Purdue UniversityHuman Pose & Activity RecognitionFitness Tracking & Physical Activity MonitoringBehavior Change & Reflection TechnologyCHI
Balancing Goals, Health, and Cost: A Food Information System for Managing Complex Choices and Fostering Sustained Food AgencyTechnology offers new opportunities to support healthier food choices, particularly for individuals in low-income communities who face systemic barriers to obtaining nutritious, affordable groceries. We introduce a novel conceptual model of grocery planning that frames food purchasing as a multi-objective optimization problem that considers cost, nutrition components, and a consumer's personal dietary goals. Guided by Zimmerman’s model of Self-Regulated Learning and prior research on food agency, we designed the Food Information System, a planning tool that provides optimized product recommendations aligned with users’ goals by integrating store inventory, prices, and nutritional data. We evaluated our system in an eight-week within-subjects intervention with 55 participants from a food-insecure community, followed by focus group sessions. While overall Healthy Eating Index scores remained largely stable, participants reported improved nutritional awareness and greater perceived agency in planning and purchasing groceries. We discuss design implications to support food agency by promoting long-term food literacy and by enhancing autonomy in making food choices.2026ASAnnalisa Szymanski et al.University of Notre DameDiet Tracking & Nutrition ManagementBehavior Change & Reflection TechnologyData-Driven Personal Decision-MakingCHI
AmIWrite: Exploring Scalable One-on-One Handwriting-Based Tutoring for Mathematical Problem-Solving with an LLM-Powered AI TutorReal-time handwriting interactions between tutors and students —where tutors observe individual problem-solving processes, provide personalized annotations, and adapt explanations based on students' work—are fundamental to effective STEM tutoring. However, scaling such personalized handwriting-based tutoring remains challenging—human tutors cannot be available to every student on demand, and current online platforms often fail to recreate equivalent learning experiences. As an initial step toward tackling this challenge, we present AmIWrite, an LLM-powered AI tutoring system for mathematical problem-solving that provides real-time co-speech handwriting interactions on tablet devices, instantiated here as a case study in linear algebra. We conducted a within-subjects study (N = 40) comparing AmIWrite to a text-based AI tutor on two linear algebra topics. Our case study demonstrates how a multimodal AI tutor can preserve the pedagogical benefits of handwriting-based math tutoring and offer a potential path toward more scalable one-on-one STEM tutoring.2026ZLZiyi Liu et al.Purdue UniversityHand Gesture RecognitionIntelligent Tutoring Systems & Learning AnalyticsTangible Interaction in EducationCHI
Out of Control: Effects of Multimodal Self-similarity on Embodiment During Autonomous Avatar Demonstrations in Virtual RealityVirtual reality (VR) training often requires autonomous avatar demonstrations, yet embodiment is strongest under direct control. We examine whether multimodal self-similarity (i.e., in appearance and voice) can preserve embodiment when control is constrained. In a 2 (self-similarity: self-similar vs. non-self-similar) $\times$ 2 (autonomy: autonomous vs. non-autonomous) within-group study, 24 participants performed a block-assembling task with self-avatars. Autonomous self-avatars increased emotional reactivity and frustration; non-autonomous self-avatars improved presence, agency, and self-attribution. Self-similarity was maintained, and self-attribution persisted during autonomous demonstrations. Tracking of head-direction (as a proxy for gaze) showed autonomy, and self-similarity increased head-based dwell on the mirror, whereas non-autonomous avatars redirected head orientation toward the body, environment, and task; an interaction effect revealed greater task-focused head-direction for non-self-similar autonomous avatars. These results indicate that autonomy and self-similarity appear to have potential additive influences on user perception in this study. We conclude that multimodal self-similarity can buffer embodiment loss during non-controllable phases and offer evidence-based guidance for designing mixed-control VR experiences.2026SGSiqi Guo et al.Purdue UniversityImmersion & Presence ResearchIdentity & Avatars in XRSocial & Collaborative VRCHI
Can AI Be a Moral Victim? The Role of Moral Patiency and Ownership Perceptions in Ethical Judgments of Using AI-Generated ContentThe growing use of generative AI raises ethical concerns about authorship attribution and plagiarism. This study examines how people judge the reuse of AI-generated content, focusing on moral patiency and ownership perceptions. In an experiment, participants evaluated two substantively similar manuscripts in which the original source was described as authored by a human, an AI system, or an AI agent with a human-like name. Results showed that copying AI-generated work was judged less unethical, less plagiaristic, and less guilt-inducing than copying human-authored work. Mediation analyses revealed that this leniency stemmed from lower perceptions of AI’s capacity to suffer harm (moral patiency) and greater ownership attributed to the human writer reusing AI-generated content. Anthropomorphic cues shaped moral evaluations indirectly by reducing perceived ownership. These findings shed light on how people morally disengage when using AI-generated work and highlight differences in how ethical judgments are applied to human versus AI-created content.2026HCHyesun Choung et al.Purdue UniversityGenerative AI (Text, Image, Music, Video)AI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasCHI